This repository contains practical exercises and projects to improve machine learning skills, covering data preprocessing, feature selection, supervised learning, and visualization. It is designed for hands-on learning with Python and commonly used ML libraries.
-
The folder structure I use:
ML-Practice/ │ ├─ Data Cleaning/ # Scripts and notebooks for cleaning and preprocessing datasets ├─ Dataset/ # Raw and processed datasets used in ML experiments ├─ Feature Selection Techniques/ # Techniques to select important features for modeling ├─ Figures/ # Visualizations and plots generated during analysis ├─ Supervised Learning/ # Implementation of supervised ML algorithms ├─ README.md # Project documentation └─ requirements.txt # Python dependencies for running the notebooks/scripts
- Data Cleaning: Handling missing values, outliers, and normalization.
- Dataset: Includes multiple datasets for practice and experimentation.
- Feature Selection Techniques: Methods like correlation analysis, recursive feature elimination (RFE), and tree-based selection.
- Figures: Visualizations such as scatter plots, histograms, and feature importance charts.
- Supervised Learning: Implementation of algorithms like Linear Regression, Logistic Regression, Decision Trees, Random Forest, and KNN.
- Clone the repository:
git clone https://github.com/yourusername/ML-Practice.git
- Navigate into the folder:
cd ML-Practice - Install dependencies:
cd ML-Practice
Explore datasets in the Dataset/ folder. Run scripts/notebooks in Data Cleaning/ to preprocess data. Apply feature selection techniques from Feature Selection Techniques/. Train and evaluate models in Supervised Learning/. View generated plots and figures in Figures/.
Add unsupervised learning projects (clustering, PCA, etc.). Include deep learning experiments using TensorFlow or PyTorch. Expand feature engineering techniques for more advanced ML practice.
Muhammad Talha
Final-year Computer Science student at UET Lahore